20 citations · 54 across the 50 of their papers we have counts for
56 papers
Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards
Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh +3
Long-horizon agents have drawn growing attention for their ability to work autonomously -- from hours to days -- on economically valuable tasks, a capability essential to automated…
Overwhelmed by Choice: Studying LLM Decision Making at Scale
Yu-Chi Lin, Aryan Seth, Anshul Aravind +4
Multiple-choice and candidate-selection evaluations are widely used to assess LLM reasoning and decision-making, yet most benchmarks contain relatively small candidate sets. It rem…
On Asymmetric Optimization of Reasoning and Perception in Vision-Language Model Post-Training
Xueqing Wu, Yu-Chi Lin, Kai-Wei Chang +1
Post-training has greatly improved reasoning in frontier vision-language models, yet its gains for perception remain comparatively limited, creating a bottleneck for end-to-end vis…
OpenVLThinkerV2: A Generalist Multimodal Reasoning Model for Multi-domain Visual Tasks
Wenbo Hu, Xin Chen, Yan Gao-Tian +3
Group Relative Policy Optimization (GRPO) has emerged as the de facto Reinforcement Learning (RL) objective driving recent advancements in Multimodal Large Language Models. However…
Beyond Facts: Benchmarking Distributional Reading Comprehension in Large Language Models
Pei-Fu Guo, Ya-An Tsai, Chun-Chia Hsu +6
While most reading comprehension benchmarks for LLMs focus on factual information that can be answered by localizing specific textual evidence, many real-world tasks require unders…
Learning Structured Reasoning via Tractable Trajectory Control
Po-Nien Kung, Zhen Yang, Jeffrey Luo +7
Large language models can exhibit emergent reasoning behaviors, often manifested as recurring lexical patterns (e.g., "wait," indicating verification). However, complex reasoning t…
LiveCLKTBench: Towards Reliable Evaluation of Cross-Lingual Knowledge Transfer in Multilingual LLMs
Pei-Fu Guo, Yun-Da Tsai, Chun-Chia Hsu +6
Evaluating cross-lingual knowledge transfer in large language models is challenging, as correct answers in a target language may arise either from genuine transfer or from prior ex…
BRIEF-Pro: Universal Context Compression with Short-to-Long Synthesis for Fast and Accurate Multi-Hop Reasoning
Jia-Chen Gu, Junyi Zhang, Di Wu +3
As retrieval-augmented generation (RAG) tackles complex tasks, increasingly expanded contexts offer richer information, but at the cost of higher latency and increased cognitive lo…
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning
Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi +2
Zero-shot Event Detection (ED), the task of identifying event mentions in natural language text without any training data, is critical for document understanding in specialized dom…
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model
Wenbo Hu, Yining Hong, Yanjun Wang +7
Humans excel at performing complex tasks by leveraging long-term memory across temporal and spatial experiences. In contrast, current Large Language Models (LLMs) struggle to effec…
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding
Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha +7
Real-world objects are composed of distinctive, object-specific parts. Identifying these parts is key to performing fine-grained, compositional reasoning-yet, large multimodal mode…
Self-Routing RAG: Binding Selective Retrieval with Knowledge Verbalization
Di Wu, Jia-Chen Gu, Kai-Wei Chang +1
Selective retrieval aims to make retrieval-augmented generation (RAG) more efficient and reliable by skipping retrieval when an LLM's parametric knowledge suffices. Despite promisi…
Enhancing LLM Character-Level Manipulation via Divide and Conquer
Zhen Xiong, Yujun Cai, Bryan Hooi +3
Large Language Models (LLMs) have demonstrated strong generalization capabilities across a wide range of natural language processing (NLP) tasks. However, they exhibit notable weak…
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles
Yihe Deng, Hritik Bansal, Fan Yin +3
We introduce OpenVLThinker, one of the first open-source large vision-language models (LVLMs) to exhibit sophisticated chain-of-thought reasoning, achieving notable performance gai…
CaKE: Circuit-aware Editing Enables Generalizable Knowledge Learners
Yunzhi Yao, Jizhan Fang, Jia-Chen Gu +4
Knowledge Editing (KE) enables the modification of outdated or incorrect information in large language models (LLMs). While existing KE methods can update isolated facts, they ofte…
MM-PoisonRAG: Disrupting Multimodal RAG with Local and Global Poisoning Attacks
Hyeonjeong Ha, Qiusi Zhan, Jeonghwan Kim +6
Retrieval-augmented generation (RAG) has become a common practice in multimodal large language models (MLLM) to enhance factual grounding and reduce hallucination. Yet, its relianc…
SYNTHIA: Novel Concept Design with Affordance Composition
Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim +7
Text-to-image (T2I) models enable rapid concept design, making them widely used in AI-driven design. While recent studies focus on generating semantic and stylistic variations of g…
Contrastive Visual Data Augmentation
Yu Zhou, Bingxuan Li, Mohan Tang +6
Large multimodal models (LMMs) often struggle to recognize novel concepts, as they rely on pre-trained knowledge and have limited ability to capture subtle visual details. Domain-s…
METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling
Bingxuan Li, Yiwei Wang, Jiuxiang Gu +2
Chart generation aims to generate code to produce charts satisfying the desired visual properties, e.g., texts, layout, color, and type. It has great potential to empower the autom…
Fact or Guesswork? Evaluating Large Language Models' Medical Knowledge with Structured One-Hop Judgments
Jiaxi Li, Yiwei Wang, Kai Zhang +5
Large language models (LLMs) have been widely adopted in various downstream task domains. However, their abilities to directly recall and apply factual medical knowledge remains un…
DRS: Deep Question Reformulation With Structured Output
Zhecheng Li, Yiwei Wang, Bryan Hooi +3
Question answering represents a core capability of large language models (LLMs). However, when individuals encounter unfamiliar knowledge in texts, they often formulate questions t…
SPEED++: A Multilingual Event Extraction Framework for Epidemic Prediction and Preparedness
Tanmay Parekh, Jeffrey Kwan, Jiarui Yu +6
Social media is often the first place where communities discuss the latest societal trends. Prior works have utilized this platform to extract epidemic-related information (e.g. in…
Control Large Language Models via Divide and Conquer
Bingxuan Li, Yiwei Wang, Tao Meng +2
This paper investigates controllable generation for large language models (LLMs) with prompt-based control, focusing on Lexically Constrained Generation (LCG). We systematically ev…
Detecting Machine-Generated Long-Form Content with Latent-Space Variables
Yufei Tian, Zeyu Pan, Nanyun Peng
The increasing capability of large language models (LLMs) to generate fluent long-form texts is presenting new challenges in distinguishing machine-generated outputs from human-wri…